shibing624/agentica — Agentica: Lightweight async-first Python framework for AI agents.

Description and use

Agentica is a lightweight, async‑first Python framework designed for building AI agents. It provides built‑in support for tool invocation, retrieval‑augmented generation (RAG), multi‑agent coordination, and multi‑choice prompting (MCP), enabling developers to orchestrate complex AI workflows with minimal overhead. The library emphasizes asynchronous execution to maximize performance in distributed or real‑time applications.

Problem

shibing624/agentica helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Agentica: Lightweight async-first Python framework for AI agents. 轻量级异步优先的AI Agent框架，支持工具调用、RAG、多智能体和MCP。

Source